University Maths Notes: Probability and Statistics – The Negative Binomial Distribution
The negative binomial distribution has the following requirements:
A sequence of independent trials.
Each trial can result in success (S) or failure (F).
The probability of success,
is
a constant.
Trials continue until r successes have been obtained.
The random variable of interest,
is
the number of failures that precede the
th
success.
may take any value greater than or equal to 0. Let
denote
the probability mass function of
The
event
is
equivalent to
S's
in the first
trials
and an S on the (
)th
trial. If
and
then
there must be four S's in the first 14 trials and the fifteenth trial
must be an S. Since the trials are independent,
![]()
The first factor here is only the binomial probability
of getting
S's
in
trials:
![]()
Multiplying this by
gives
![]()
Like the normal binomial expansion, the negative binomial distribution is well defined even when r is not an integer. In this case we have the generalized negative binomial distribution.
The mean and variance are given by
and![]()
Example: A paediatrician wishes to recruit five
couples, each expecting their first child. Let
be the probability that the couple agree to be recruited. What is the
probability that fifteen couples are asked before the required five
agree?
We have
and![]()
![]()